B0979
Title: Subject-wise empirical likelihood inference in partial linear models for longitudinal data
Authors: Lianfen Qian - Florida Atlantic University (United States) [presenting]
Suojin Wang - Texas A and M University (United States)
Abstract: In analyzing longitudinal data, within-subject correlations are a major factor that affects statistical efficiency. Working with a partially linear model for longitudinal data, we consider a subject-wise empirical likelihood based method that takes into consideration the within-subject correlations to estimate the model parameters efficiently. A nonparametric version of the Wilks' theorem for the limiting distribution of the empirical likelihood ratio, which relies on a kernel regression smoothing method to properly centered data, is derived. We also consider the estimation of the nonparametric baseline function. A simulation study and an application are reported to investigate the finite sample properties of the proposed method and compare it with the block empirical likelihood method. These numerical results demonstrate the usefulness of the proposed method.